Many biomedical organizations today want to harness the power of big data analytics and machine learning for its potential to improve margins, enhance discoveries and diagnostics, and enable fast data driven decisions. At Biosymetrics Inc., they are using our zero latency machine learning and analytics dataset to integrate multiple data types in the biosciences with the goal of discoveries and approaches in ‘Precision Medicine’. Their goal has been to cut the memory footprint required to learn large data sets, select the best attributes for model creation, build thousands of models on the fly, and do this with multiple data types. They have been developing an imaging pipeline for fMRI and MRI images and have also built similar pipelines for genomics, drug discovery and clinical data. These pipelines carry out preprocessing functions and feature selection and prepare the data for inclusion into AugustaTM, their real-time machine learning technology.
Objectives:
This course will explore some of the functionality of their platform including their precision medicine pipelines in Python and use of real-time machine learning through AugustaTM. This includes real time exploration of data, fast multi-variate model generation, use of GPUs and parallelization and distribution with Apache Spark. The course will discuss key components of their pipelines integrated with real-time machine learning that contribute to our goal of developing solutions for precision medicine and they will include some visualization capabilities using an example from Finance.
Participation Requirements:
The workshop will be hands-on and participants should bring their laptops and have Python installed. We will make AugustaTM instances available to all participants.
Instructors:
Dr. Shiva Amiri
As the CEO of BioSymetrics Inc., Shiva is working on delivering a unique real-time machine learning technology for the analysis of massive data in the biomedical space. Prior to BioSymetrics Inc. she was Chief Product Officer of Real Time Data Solutions Inc., she has lead the Informatics and Analytics team at the Ontario Brain Institute, and she is also the President and CEO of Modecular Inc., a Computational Biochemistry start-up company developing next generation drug screening methodologies. Shiva completed her D.Phil. (Ph.D.) in Computational Biochemistry at the University of Oxford and her undergraduate degree in Computer Science and Human Biology at the University of Toronto. Shiva is involved with several organisations including Let’s Talk Science and Shabeh Jomeh International.
Dr. Gabe Musso
As VP, Life Sciences at BioSymetrics Inc., Gabe is focused on growing the AugustaTM platform and applying it in the areas of genomics, imaging and clinical diagnosis. Prior to joining BioSymetrics Inc., Gabe was an Associate Scientist at Brigham and Women’s Hospital where his work focused on using machine learning frameworks to predict gene and small molecule function, and identification of disease-causal genes using large-scale genomic datasets. Gabe received his Ph.D. in Molecular Genetics from the University of Toronto. He also received his Master’s of Science and undergraduate degree from the University of Toronto.
Dr. Babak Afshin-Pour, VP Technology
Babak Afshin-Pour is the VP of Technology at BioSymetrics Inc. and has been putting in place a unique platform for the complex data types which BioSymetrics works with in the medical space. His interests are in the areas of big data analytics, advanced medical signal and image processing, evaluation and optimizing of fMRI analysis techniques, graph theoretical network analysis, and analysis of multi-site neuroimaging data. His proposed analysis frameworks have been published in high impact journals such as HBM, NeuroImage, and TMI. Babak received a B.S, degree in biomedical engineering as well as his M.S. and Ph.D. in electrical engineering from the University of Tehran with distinction. After the Ph.D., he was awarded a three-year post-doctoral fellowship at the Rotman Research Institute, University of Toronto.
Anatoly Likhatchev, VP Fintech
Anatoly Likhatchev, MSc has close to 20 years of experience in consulting and business development in areas of finance, information technology, biotechnology, automated trading systems, e-commerce, human resources and manufacturing. He has extensive knowledge in technical trading on the stock markets and has devoted his Master’s Thesis completed at McGill University in Montreal, Canada to developing automated trading systems using neural nets and genetic algorithms. In his role as VP, Financial Services, he has created a unique Financial Modeling Environment for the prediction of market moves. Anatoly is fluent in English and Russian and competent in French and Spanish. He is working on his proficiency in German, Italian, Portuguese, Dutch, Danish, Irish, Arabic, and Mandarin. He is currently a CFA Level III Candidate.
